Advanced Glyph Interpretation Framework for Antiquated Writings

Manuscripts are valuable cultural heritage materials. There are important sources of culture in the history of the region. The use of primary sources such as diaries, government documents and newspaper articles exposes important historical concepts. Many of the English historical documents have been affected by water, fungi, incendiary and alien invaders. Manuscripts are deteriorated due to different causes such as moisture, dust, contamination of the atmosphere, fragility and microbiological mismanagement. In todays digital era, it is necessary to keep all the available information in digital form. Handwritten identification of characters using digital imaging technology is a key move in many documents and analytical applications. When older documents are converted into text, difficulties arise that cause the performance of the OCR tools to decrease. One of the problems of historical documents is that the quality of the print medium has often degraded over time. The quality of the paper also impacts the output, as in some cases the letters on the reverse side of a page are visible in the scanned image, which adds noise to the document. Furthermore, OCR systems are generally best suited to contemporary texts, and not built to handle the typefaces and linguistic conventions that characterize older documents.